Liwei Jiang

liweijiang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset 3 days ago

liweijiang/socres_0000

Viewer • Updated 3 days ago • 5 • 7

updated 3 datasets 4 days ago

liweijiang/relative-harm-annotation1

Viewer • Updated 4 days ago • 15 • 20

liweijiang/relative-harm-annotation2

Viewer • Updated 4 days ago • 5 • 29

liweijiang/relative-harm-annotation

Viewer • Updated 4 days ago • 5 • 8

liked a model 6 days ago

meta-llama/Llama-3.2-3B-Instruct

Text Generation • Updated Oct 24 • 2.15M • • 820

updated a dataset 5 months ago

allenai/wildjailbreak

Viewer • Updated Aug 8 • 2.21k • 1.19k • 26

liked a dataset 6 months ago

allenai/wildjailbreak

Viewer • Updated Aug 8 • 2.21k • 1.19k • 26

authored a paper 6 months ago

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Paper • 2406.18510 • Published Jun 26 • 8

upvoted 2 papers 6 months ago

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Paper • 2406.18495 • Published Jun 26 • 12

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Paper • 2406.18510 • Published Jun 26 • 8

commented a paper 6 months ago

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Paper • 2406.18510 • Published Jun 26 • 8 •

1

updated a collection 6 months ago

AI2 Safety Toolkit

Collection

Safety data, moderation tools and safe LLMs. • 6 items • Updated 28 days ago • 3

liked a dataset 11 months ago

allenai/WildChat

Viewer • Updated Oct 17 • 529k • 642 • 129

authored a paper about 1 year ago

The Generative AI Paradox: "What It Can Create, It May Not Understand"

Paper • 2311.00059 • Published Oct 31, 2023 • 18